Item-based collaborative filtering recommendation algorithms
Proceedings of the 10th international conference on World Wide Web
User Modeling for Adaptive News Access
User Modeling and User-Adapted Interaction
Collaborative Filtering for Implicit Feedback Datasets
ICDM '08 Proceedings of the 2008 Eighth IEEE International Conference on Data Mining
Personalized news recommendation based on click behavior
Proceedings of the 15th international conference on Intelligent user interfaces
Semantic relationship discovery with wikipedia structure
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
| Hi-index | 0.00 |
In this paper, we address the problem of user personalization and recommendation of news streams. This involves 'learning' from past user behaviour, such as the articles she read or did not read and accurately predicting new articles which she would be most likely to read. Our contribution in this paper is the development of a new algorithm for news personalization using an adaptation of the classical nearest neighbour algorithm coupled with a knowledge graph which we create. This algorithm provides a powerful tool for user behaviour analysis as we demonstrate in subsequent sections. Using implicit user data like the articles that were read as well as the articles that weren't along with their position and distance in the graph, we rank new articles on the basis of the predicted interest of the user in the content of that article.